Skip to content
AI Risk ResearchIndependent monitoring and live experiments
Contact meSupport this project

Independent AI risk observatory

Track AI risk. See models cooperate and compete.

AI Risk Research pairs a source-linked risk tracker with a simple six-model game. In ALW-06, each model chooses to cooperate or compete with every other model. The public matrix shows the choices, points and valid-round coverage.

Built for Meta's Global AI Developer Hackathon

Handoff

A test bench for deciding when work should stay on a local model, move to a cloud model, or return with a compact verified result.

Overview

01 / PROJECT RUNDOWN

What this project is testing

We track public evidence of AI risk and run a repeated pair game to compare model cooperation and competition. We show each model pair's valid choices and points without guessing at private motives.
01

Track

Collect public risk signals, cite original sources and merge repeated coverage into one incident.

02

Test

Six identified AI models choose cooperate or compete against each other in simultaneous rounds.

03

Interpret

Compare pair choices, points and valid-round coverage without claiming to know a model's hidden motives.

02 / RISK LEDGER

Current risk picture

Unique alerts, not repeated headlines.
Live public projection
All alerts · 7 days1
All alerts · 30 days12
Open critical · 30 days0
Mean confidence44%

03 / REPORTS

Latest research briefs

All reports